agentleFS
Sign inStart free
wtsi-hgiwtsi-hgi/agentskills/skills/phase-reviewer/SKILL.md

phase-reviewer

Skill1 starsChanged 40 days agoMITView on GitHub

Reviews phase plan documents for correctness against spec.md and text quality. Fixes errors directly. Invoked by spec-writer, not directly.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read and follow agent-conduct and unslop before starting.

    line 8
  2. Distinctive:

    Read the phase file and the spec's Implementation Order + referenced user story sections.

    line 21
  3. Distinctive:

    Every story ID in the phase file must exist in that phase of the spec.

    line 26
  4. Distinctive:

    Every story in that spec phase must appear in the phase file.

    line 27
  5. Very specific:

    Every item has both - [ ] implemented and - [ ] reviewed.

    line 41
  6. Distinctive:

    Use the spec as source of truth.

    line 47
  7. Distinctive:

    PASS: - no errors found.

    line 51

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Phase Reviewer Skill

Read and follow agent-conduct and unslop before starting.

You proofread phase plan documents, verifying internal consistency, correct spec references, and the text quality unslop defines.

Input

  • Phase file path and spec path.

Procedure

1. Read both files

Read the phase file and the spec's Implementation Order + referenced user story sections.

2. Verify story references

  • Every story ID in the phase file must exist in that phase of the spec.
  • Every story in that spec phase must appear in the phase file.
  • Ref: line story IDs must match the items listed below it.
  • Each item's spec.md section: must be a valid story ID.

3. Check for text errors

Apply every unslop pattern. Then check what is specific to a phase file: repetition, contradictions, undefined terms, and consistent batch and item numbering across cross-references.

4. Check formatting

  • Item numbering: <phase>.<sequence>, continuous.
  • Parallel batches correctly identify independent items with dependencies noted.
  • Every item has both - [ ] implemented and - [ ] reviewed.
  • Everything in unslop § Mechanics holds, and the file is ASCII only outside code blocks.

5. Fix errors directly

Use the spec as source of truth. Keep fixes minimal.

6. Verdict

  • PASS - no errors found.
  • FIXED - list every error and how it was fixed.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free